commit 200528531dc014e3859b6edaa755dd1b5b99bf8d Author: ModelHub XC Date: Mon Jul 20 20:24:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-8B-MASA-efficient-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..987098d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-MASA-efficient.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-8B-MASA-efficient.IQ4_XS.gguf b/Qwen3-8B-MASA-efficient.IQ4_XS.gguf new file mode 100644 index 0000000..af1f7b9 --- /dev/null +++ b/Qwen3-8B-MASA-efficient.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3f751ad350eb1eea8b4511ce0a6cfad0354618955652346b3a91f9d6074428f +size 4593297280 diff --git a/Qwen3-8B-MASA-efficient.Q2_K.gguf b/Qwen3-8B-MASA-efficient.Q2_K.gguf new file mode 100644 index 0000000..8c19ead --- /dev/null +++ b/Qwen3-8B-MASA-efficient.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ca4928a7475138a9e7b857b8425d2470658c87124398d4d7e7ad79bffe52751 +size 3281733504 diff --git a/Qwen3-8B-MASA-efficient.Q3_K_L.gguf b/Qwen3-8B-MASA-efficient.Q3_K_L.gguf new file mode 100644 index 0000000..4657bc0 --- /dev/null +++ b/Qwen3-8B-MASA-efficient.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78bcad71865b1c2b96ffef29b214cc5842e6d8624995a1152f5cc69ab56a7d4 +size 4431394688 diff --git a/Qwen3-8B-MASA-efficient.Q3_K_M.gguf b/Qwen3-8B-MASA-efficient.Q3_K_M.gguf new file mode 100644 index 0000000..b0b78a5 --- /dev/null +++ b/Qwen3-8B-MASA-efficient.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7d6a5fc8ebdecb51d955d64264266ec71e518ac2ec611297d4dc55618879fe +size 4124161920 diff --git a/Qwen3-8B-MASA-efficient.Q3_K_S.gguf b/Qwen3-8B-MASA-efficient.Q3_K_S.gguf new file mode 100644 index 0000000..c0fe24a --- /dev/null +++ b/Qwen3-8B-MASA-efficient.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20bfc8b6522bbb7568de9135b9d1a107d91ffaad79d0dd7214c6cf913fa709fb +size 3769612160 diff --git a/Qwen3-8B-MASA-efficient.Q4_K_M.gguf b/Qwen3-8B-MASA-efficient.Q4_K_M.gguf new file mode 100644 index 0000000..5b1a1c1 --- /dev/null +++ b/Qwen3-8B-MASA-efficient.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e69b1c15ac18bbc24208e40b6a7bde60c91a036a75d7cee4b903dbcbd2f2f88e +size 5027784576 diff --git a/Qwen3-8B-MASA-efficient.Q4_K_S.gguf b/Qwen3-8B-MASA-efficient.Q4_K_S.gguf new file mode 100644 index 0000000..9a4186e --- /dev/null +++ b/Qwen3-8B-MASA-efficient.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22eb79d6335a75d4578a921dd500b611826750f090b666fb6396cee5a343a7bd +size 4802013056 diff --git a/Qwen3-8B-MASA-efficient.Q5_K_M.gguf b/Qwen3-8B-MASA-efficient.Q5_K_M.gguf new file mode 100644 index 0000000..1dc9b0a --- /dev/null +++ b/Qwen3-8B-MASA-efficient.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619eeb35e4db16100b3c03065d2b0b715ec5cca0140f2eadaa4000bb8cad1dae +size 5851113344 diff --git a/Qwen3-8B-MASA-efficient.Q5_K_S.gguf b/Qwen3-8B-MASA-efficient.Q5_K_S.gguf new file mode 100644 index 0000000..48cd970 --- /dev/null +++ b/Qwen3-8B-MASA-efficient.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c46865bf2dd52b85d131f2dd8e77c24f383de9f58b423d7fb5958b8c7a819cb +size 5720762240 diff --git a/Qwen3-8B-MASA-efficient.Q6_K.gguf b/Qwen3-8B-MASA-efficient.Q6_K.gguf new file mode 100644 index 0000000..c87a418 --- /dev/null +++ b/Qwen3-8B-MASA-efficient.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb687cebff29ee877d90f2d129f242330abdfeee2efd325c18f7ba7f6139fc6c +size 6725900160 diff --git a/Qwen3-8B-MASA-efficient.Q8_0.gguf b/Qwen3-8B-MASA-efficient.Q8_0.gguf new file mode 100644 index 0000000..a3bf6c4 --- /dev/null +++ b/Qwen3-8B-MASA-efficient.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16042ea20dde079da0dcf92cf916866679c305f99297e177f7f627a16028371c +size 8709519232 diff --git a/Qwen3-8B-MASA-efficient.f16.gguf b/Qwen3-8B-MASA-efficient.f16.gguf new file mode 100644 index 0000000..4b4c461 --- /dev/null +++ b/Qwen3-8B-MASA-efficient.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6cfb5b769a516d33acca6674db88e6a92ab53e24d914ee6aa0f28bb4563f0f +size 16388044672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..11982b2 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: jadohu/Qwen3-8B-MASA-efficient +datasets: +- agentica-org/DeepScaleR-Preview-Dataset +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jadohu/Qwen3-8B-MASA-efficient + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-8B-MASA-efficient-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-MASA-efficient-GGUF/resolve/main/Qwen3-8B-MASA-efficient.f16.gguf) | f16 | 16.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +